DATA SCIENCE IN FINANCE

Let’s get started! Meet your instructor and discuss the course objectives. Get your Python environment setup, and get any questions you have answered. 

• Instructor Introduction
• Course Objectives & Flow
• Python environment setup
• Introduction of project assignment and key dates
• Q & A

Uncover the power of AI and ML in finance. Start to decode key terminology and dive into the Machine Learning workflow.

• What is data science, AI & ML?
• Key applications in financial services
• Key skills for a data scientist or data engineer 
• Key terminology and software related to financial services
• Machine Learning pipeline & workflow

Learn how to proficiently acquire and clean financial datasets using Python. You’ll cover data sourcing and cleaning techniques as well as addressing common challenges such as imbalanced data.

• Common data sources for data science and AI in finance
• Common data gathering and cleaning techniques and implementation in Python
• Case Study: Addressing common challenges in financial data
• Workshop: Hands-on data cleaning techniques using Python

Get equipped with the skills you need to explore and analyse data in Python. You’ll be able to derive actionable insights through techniques including summary statistics, visualisation and time series analysis.

• Data exploratory analysis and uses in finance
• Feature engineering and its use in data science
• How visualisation can boost your EDA process
• Time series data and how to treat it in EDA
• Demo: Implementation in Python

Assignment #1: Data cleaning and uncovering additional actionable insights as an outcome of EDA.

Get familiar with statistical modelling and gain foundational skills in finance using Python. You’ll cover hypothesis testing, the Central Limit Theorem, and practical applications such as creditworthiness assessment.

• Introduction to statistical modelling and use cases in finance
• How to make inferences and validate business hypotheses with your data 
• Workshop: Creditworthiness Assessment

Deep dive into machine learning and artificial intelligence. Discover methods of building and evaluating classification models for risk assessment. Get familiar with ethical considerations, managing bias, and balancing model accuracy with interpretability. 

• Introduction to Machine Learning and Artificial Intelligence
• AI & ML algorithms
• Building classification models for risk assessment
• Evaluating and interpreting ML models for risk
• Balancing model accuracy and interpretability
• Common challenges in modelling and techniques to handle them
• Demo: E2E model training and evaluation flow 

Assignment #2: Build a baseline model and optimise profitability of a lending book based on credit history.

Start your journey to mastering ensemble techniques in machine learning - and understanding their use cases in Finance. Grasp the importance of Model interpretability and explainability frameworks in this specific industry, and get an introduction to hyperparameter tuning.

• Ensemble models in Machine Learning
• Model interpretability and explainability frameworks
• Introduction to Hyperparameter Tuning
• Demo: Implement an ensemble model, performing hyperparameter tuning and compare performance to the baseline model built in session 4 

Ready for your introduction to deep learning and neural networks? Focus in on their relevance in finance, and learn about the most popular Python frameworks for implementation.

• Introduction to Deep Learning and Neural Networks 
• Understanding how these are used in Finance
• Demo: Popular Python frameworks for neural networks

Assignment #3: Build a challenger model to baseline model built in Assignment #2, using concepts from Session 6 and 7.

Gain the key skills you need to excel in unsupervised learning for finance. You’ll cover outlier detection techniques, strategies for customer segmentation, and dimensionality reduction methods such as principal component analysis.

• Outlier detection: use cases and techniques in financial services
• Clustering and segmentation use cases 
• Principal component analysis for dimensionality reduction
• Demo: Implementation in Python

Assignment #4: Segment a credit card customer base into groups for marketing and customer management purposes.

It’s time to master time series modelling in financial services. Start to understand time series data, decomposition techniques and get familiar with foundational forecasting methods.

• Time series data and use cases in finance
• Decomposing time series data into its key components
• Forecasting methods and model families
• Demo: Implementation in Python

Assignment #5 (optional): Forecasting exercise

Delve deep into Generative AI and Large Language Models. You’ll gain a critical understanding of their functionality and applications in financial services. Explore adoption patterns, risks and opportunities, with a practical demonstration on building a customer service chatbot.

• Introduction to Generative AI and Large Language Models
• Adoption patterns in financial services, risks and opportunities
• Demo: build a customer services chatbot
• Guest speaker

Grasp the opportunity to build a real-time fraud detection app in Python. You’ll get a detailed introduction to app development, a hands-on workshop, and considerations on scalability and design.

• Introduction to building apps in Python 
• Workshop: Build a fraud detection app
• Considerations on app scalability and design

Assignment #6 (optional): Build your own app

Get to know ML system design, the ML Ops lifecycle and model governance. Look critically at insights into ethical considerations, data privacy, security concerns, and regulatory compliance in AI deployment within the finance sector.

• ML system design and architecture
• ML Ops lifecycle and model governance
• Ethical considerations of AI in finance
• Data privacy & security concerns
• Regulations and compliance

Assignment #7 (optional): Write architecture diagram for your modelling solution

Want to learn to deliver data science projects effectively? Dive deeper into how to measure success, apply coding best practices, collaborate efficiently, and stay updated on cloud technologies and industry trends.

• Effective data science project delivery
• Measuring success and ROI
• Workshop: Define success for your data science initiative
• Coding and software development best practices
• Effective collaboration
• The rise of cloud and trends in data science industry

Assignment #8: Push code to git

Plot your career path in data science within finance with a strategic planning session designed to start your ascent. Discuss key trends in AI as well as the future of finance. Get guidance on how to prepare your CV and how to stand out at interviews. 

• Career paths in Data science in finance
• Key trends and AI & finance future
• CV preparation & interview guidance
• Course wrap up

Final Project: 

• A comprehensive report documenting the entire process; from data cleaning to model development and deployment. Give clear explanations of methodologies used and architecture considerations
• Code base in Python
• Visualisations communicating key insights derived from the financial dataset
• A presentation where you will effectively communicate findings and decisions to simulate real-world scenarios